A3) Consider the system described by the transfer function. G(S) = 45 + 45+8 252+ 65+ 4 a) (5pts) Write down the controllable canonical form. b) (5pts) Write down the observable canonical form. c) (10pts) Let Xc denotes the state vector for the controllable canonical form and X for the observable canonical form. Find the transformation matrix P such that Xc = PXo. Solution:Please convert from canonical form to standard form! Canonical Form to Standard Form 2. Convert the following expression from standard form (3 variables) to canonical form (sum-of-minterms) : F = (ab' + c')c + (b + c)'Exercise 1 {It points] \"Thich of the following statements is true?I {a} logistic regression is a parametric model while random forest is a nonparametric model. {b} logistic regression is a nonparametric mode] while random forest is a parametric model. {C} logistic regression and random forest are both parametric models. {d} logistic regression and random forest are both nonparametric models. [El All of the above. [f] None of the above. Question 1 {1 point) X Saved Normal Distributions are required for: O Parametric Statistics 0 NonParametric Statistics 6) Regression Analysis 0 Parametric Statistics & Regression Analysis 0 All of the other answers Part one - evalboostforest( ) _ 1. Import alpha and trained model 2. Derive prediction using alphalil * treelil.predict(xTe) Part two - GBRT( ) function when i = 1 1. Import Regression Tree model 2. Train Regression Tree with xTr and yTr training data 3. Append trained model and alpha o trees = tree(xTryTr) 4. Derive the prediction (PredHi) using evalboostforest0 function predHi = alpha' tree(xTr. yTr) when i = 2 1. Import Regression Tree model 2. Train Regression Tree with xTr and residual(yTr - PredHi) training data 3. Append trained model and alpha o trees = tree(xTr. yTr) + tree(xTr, yTr - PredH1) 4. Derive the prediction (PredH2) using evalboostforest() function predH2 = alpha' tree(xTr, yTr) + alpha ' tree(xTr. yTr - PredH1) when i = 3 1. Import Regression Tree model 2. Train Regression Tree with xTr and residual(yTr - PredHi) training data 3. Append trained model and alpha trees = tree(xTr. yTr) + tree(xTr, yTr - PredH1) + tree(xTr, yTr - PredH2) 4. Derive the prediction (PredH2) using evalboostforest() function predH3 = alpha ' tree(xTr. yTr) + alpha' tree(xTr, yTr - PredHi) + alpha' tree(xTryTr - PredH2)